Conference item
Learning to round for discrete labeling problems
- Abstract:
-
Discrete labeling problems are often solved by formulating them as an integer program, and relaxing the integrality constraint to a continuous domain. While the continuous relaxation is closely related to the original integer program, its optimal solution is often fractional. Thus, the success of a relaxation depends crucially on the availability of an accurate rounding procedure. The problem of identifying an accurate rounding procedure has mainly been tackled in the theoretical computer sci...
Expand abstract
- Publication status:
- Published
- Peer review status:
- Peer reviewed
Actions
Authors
Funding
+ Engineering and Physical Sciences Research Council
More from this funder
Grant:
EP/P020658/1
TU/B/000048
Bibliographic Details
- Publisher:
- PMLR Publisher's website
- Journal:
- 21st International Conference on Artificial Intelligence and Statistics (AISTATS) 2018 Journal website
- Volume:
- 84
- Pages:
- 1047-1056
- Series:
- Proceedings of Machine Learning Research
- Host title:
- Proceedings of the 21st International Conference on Artificial Intelligence and Statistics (AISTATS) 2018
- Publication date:
- 2018-03-31
- Acceptance date:
- 2017-12-22
- ISSN:
-
1938-7228
- Source identifiers:
-
826797
Item Description
- Pubs id:
-
pubs:826797
- UUID:
-
uuid:a92ece28-d8b1-4498-b7e6-c67f6301756e
- Local pid:
- pubs:826797
- Deposit date:
- 2018-02-27
Terms of use
- Copyright holder:
- Mohapatra et al
- Copyright date:
- 2018
- Notes:
-
Copyright 2018 by the
authors. This is the accepted manuscript version of the article. The final version is available online from PMLR at: http://proceedings.mlr.press/v84/mohapatra18a.html
If you are the owner of this record, you can report an update to it here: Report update to this record